Culturally Attuned and Resource-Aware Foundation Models for East African Agriculture: A Theoretical Framework and Research Agenda

Innocent Nyalala, Nirav Bhatt
DLI 2025 Research Track, PMLR 302:1-11, 2026.

Abstract

East African agriculture supports more than 175 million people but faces mounting challenges from climate change, resource constraints, and information access barriers. Current foundation models fail to address the region’s computational limitations (devices with 1-4GB RAM), linguistic diversity (200+ languages), and knowledge system differences. This paper presents CARA-FM (Culturally Attuned and Resource-Aware Foundation Models), a theoretical framework comprising four pillars: Community-Driven Data Architecture, Indigenous Knowledge Systems, Edge-First Model Design, and Participatory Governance. We propose evaluation metrics that span the technical (computational efficiency), agricultural (yield improvement), and cultural (community acceptance) dimensions. Although empirically unvalidated, this framework provides a research agenda for developing agricultural AI systems that operate within severe resource constraints and respect local contexts. Our contribution is theoretical and offers a blueprint for future empirical work rather than implemented solutions. Keywords: Foundation Models, Agricultural AI, Theoretical Framework, East Africa, Resource-Constrained Computing, Indigenous Knowledge.

Cite this Paper

BibTeX
@InProceedings{pmlr-v302-nyalala26a, title = {Culturally Attuned and Resource-Aware Foundation Models for East African Agriculture: A Theoretical Framework and Research Agenda}, author = {Nyalala, Innocent and Bhatt, Nirav}, booktitle = {DLI 2025 Research Track}, pages = {1--11}, year = {2026}, editor = {Haddad, Hatem and Kahira, Albert Njoroge and Bourhim, Sofia and Olatunji, Iyiola Emmanuel and Makhafola, Lesego and Mwase, Christine}, volume = {302}, series = {Proceedings of Machine Learning Research}, month = {17--22 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v302/main/assets/nyalala26a/nyalala26a.pdf}, url = {https://proceedings.mlr.press/v302/nyalala26a.html}, abstract = {East African agriculture supports more than 175 million people but faces mounting challenges from climate change, resource constraints, and information access barriers. Current foundation models fail to address the region’s computational limitations (devices with 1-4GB RAM), linguistic diversity (200+ languages), and knowledge system differences. This paper presents CARA-FM (Culturally Attuned and Resource-Aware Foundation Models), a theoretical framework comprising four pillars: Community-Driven Data Architecture, Indigenous Knowledge Systems, Edge-First Model Design, and Participatory Governance. We propose evaluation metrics that span the technical (computational efficiency), agricultural (yield improvement), and cultural (community acceptance) dimensions. Although empirically unvalidated, this framework provides a research agenda for developing agricultural AI systems that operate within severe resource constraints and respect local contexts. Our contribution is theoretical and offers a blueprint for future empirical work rather than implemented solutions. Keywords: Foundation Models, Agricultural AI, Theoretical Framework, East Africa, Resource-Constrained Computing, Indigenous Knowledge.} }
Endnote
%0 Conference Paper %T Culturally Attuned and Resource-Aware Foundation Models for East African Agriculture: A Theoretical Framework and Research Agenda %A Innocent Nyalala %A Nirav Bhatt %B DLI 2025 Research Track %C Proceedings of Machine Learning Research %D 2026 %E Hatem Haddad %E Albert Njoroge Kahira %E Sofia Bourhim %E Iyiola Emmanuel Olatunji %E Lesego Makhafola %E Christine Mwase %F pmlr-v302-nyalala26a %I PMLR %P 1--11 %U https://proceedings.mlr.press/v302/nyalala26a.html %V 302 %X East African agriculture supports more than 175 million people but faces mounting challenges from climate change, resource constraints, and information access barriers. Current foundation models fail to address the region’s computational limitations (devices with 1-4GB RAM), linguistic diversity (200+ languages), and knowledge system differences. This paper presents CARA-FM (Culturally Attuned and Resource-Aware Foundation Models), a theoretical framework comprising four pillars: Community-Driven Data Architecture, Indigenous Knowledge Systems, Edge-First Model Design, and Participatory Governance. We propose evaluation metrics that span the technical (computational efficiency), agricultural (yield improvement), and cultural (community acceptance) dimensions. Although empirically unvalidated, this framework provides a research agenda for developing agricultural AI systems that operate within severe resource constraints and respect local contexts. Our contribution is theoretical and offers a blueprint for future empirical work rather than implemented solutions. Keywords: Foundation Models, Agricultural AI, Theoretical Framework, East Africa, Resource-Constrained Computing, Indigenous Knowledge.
APA
Nyalala, I. & Bhatt, N.. (2026). Culturally Attuned and Resource-Aware Foundation Models for East African Agriculture: A Theoretical Framework and Research Agenda. DLI 2025 Research Track, in Proceedings of Machine Learning Research 302:1-11 Available from https://proceedings.mlr.press/v302/nyalala26a.html.

Related Material